Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/antimetal/cursor-pluginWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/rules/antimetal/cursor-plugin/antimetal-conventions)<a href="https://agentmods.dev/rules/antimetal/cursor-plugin/antimetal-conventions"><img src="https://agentmods.dev/badge/rules/antimetal/cursor-plugin/antimetal-conventions/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/rules/antimetal/cursor-plugin/antimetal-conventions"><img src="https://agentmods.dev/badge/rules/antimetal/cursor-plugin/antimetal-conventions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00590 | $0.00590 |
| Opus 5.5 | $0.00236 | $0.00236 |
| Sonnet 5.5 | $0.00118 | $0.00118 |
| Haiku 4.5 | $0.00059 | $0.00059 |
Grade A, and why
antimetal-conventions scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
antimetal-conventions:
- API key required: All MCP tools need a valid
ANTIMETAL_API_KEYenvironment variable. If a tool call fails with an auth error, prompt the user to set it:export ANTIMETAL_API_KEY="your-key"(get one at antimetal.com under account settings). Suggest adding it to their shell profile so it persists. - When referencing Antimetal issues, prefer the issue number (e.g., #42) over the UUID for readability.
- Artifact IDs follow the format
type:provider:id(e.g.,log:datadog:a9c131...,trace:gcp:abc123). These come fromdocumentIdfields in causal graph evidence nodes. - Issue statuses are:
investigating,ready_to_fix,resolved,muted. - Issue severities are:
high,medium,low. - When applying remediations, always verify code changes against the local codebase before committing.
- The
asktool supports multi-turn conversations viaconversation_id-- always pass it for follow-ups.
MCP Tools
| Tool | Purpose |
|---|---|
search_issues |
Paginated issue list with filters (status, environment, search text) |
get_issue_report |
Full investigative report—root cause, timeline, causal graph |
get_issue_fixes |
Remediation steps for a specific issue |
investigate_issue |
Create a new issue and start async automated investigation (3-10 min) |
get_artifact |
Retrieve raw evidence by document ID (metrics, traces, logs, files, events, topology) |
ask |
Query Antimetal's AI about infrastructure, software, deployments, telemetry, logs, code -- supports follow-up via conversation_id |
Causal Graph Concepts
- Node types:
outcome(what broke),cause(why it broke),confounder(correlated but not causal),mediator(how the cause propagated) - Confidence levels (ordered):
confirmed>likely>probable>unclear>unknown - Distinguish causes from confounders -- correlation is not causation
- Mediators show the propagation path from cause to outcome
Remediation Step Types
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 39 lines · 590 tokens per session scan A 3c18e750f87d
antimetal-conventions is a cursor rule published in the GitHub repository antimetal/cursor-plugin (4 stars, last pushed 4mo ago), licensed MIT. It adds 590 tokens to every session, about $0.0024 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other cursor rules, from other repositories
error-handling-and-validation
A code-quality guide for handling errors, invalid inputs, edge cases, preconditions, logging, and user-friendly error messages.
css-render-blocking-diagnosis
Cursor rule "css-render-blocking-diagnosis" from adobecom/da-express-milo, covering css render-blocking diagnosis & resolution, critical learning from 98 pagespeed achievement, primary diagnostic protocol, step 1: css blocking symptom recognition and step 2: css loading sequence audit.
javascript-expert-performance
Profile first. Measure before and after. Never optimize without data.
5-bug-finder
APPLY WHEN investigating a bug.
optimisation-rules
Performance optimization with evidence-based improvements.
dockerfile-conventions
Enforce Dockerfile best practices: multi-stage builds, non-root USER, no secrets in ENV/ARG, and .dockerignore hygiene.